Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3214 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.9676. Min Act: -0.0002

Data Index: 1073898 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.9225. Min Act: -0.0002

Data Index: 1087504 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.9243. Min Act: -0.0002

Data Index: 1159430 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.9009. Min Act: -0.0002

Data Index: 1010555 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.9048. Min Act: -0.0002

Data Index: 1220620 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.9005. Min Act: -0.0002

Data Index: 673082 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8557. Min Act: -0.0002

Data Index: 661116 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8657. Min Act: -0.0002

Data Index: 1226623 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8847. Min Act: -0.0002

Data Index: 1223603 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8527. Min Act: -0.0002

Data Index: 826556 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8514. Min Act: -0.0002

Data Index: 877509 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8412. Min Act: -0.0002

Data Index: 1354506 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8393. Min Act: -0.0002

Data Index: 766328 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8277. Min Act: -0.0002

Data Index: 865800 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8137. Min Act: -0.0002

Data Index: 39310 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8219. Min Act: -0.0002

Data Index: 827246 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8186. Min Act: -0.0002

Data Index: 1004828 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8001. Min Act: -0.0002

Data Index: 1164474 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.8033. Min Act: -0.0002

Data Index: 751216 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 0.9676. Min Range: -0.9676

Max Act: 0.7870. Min Act: -0.0002

Data Index: 697229 (C4 (Web Text))

Max Activating Token Index: 29